Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.37 as permitted sender) client-ip=23.128.96.37;
Date:   Tue, 24 Oct 2023 15:23:23 -0700
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>
Message-Id: <20231024222353.3024098-21-irogers@google.com>
Mime-Version: 1.0
References: <20231024222353.3024098-1-irogers@google.com>
Subject: [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer
From:   Ian Rogers <irogers@google.com>
To:     Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@kernel.org>,
        Namhyung Kim <namhyung@kernel.org>,
        Ian Rogers <irogers@google.com>,
        Adrian Hunter <adrian.hunter@intel.com>,
        Nick Terrell <terrelln@fb.com>,
        Kan Liang <kan.liang@linux.intel.com>,
        Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
        Song Liu <song@kernel.org>,
        Sandipan Das <sandipan.das@amd.com>,
        James Clark <james.clark@arm.com>,
        Anshuman Khandual <anshuman.khandual@arm.com>,
        Miguel Ojeda <ojeda@kernel.org>,
        Liam Howlett <liam.howlett@oracle.com>,
        Yang Jihong <yangjihong1@huawei.com>,
        Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
        Kajol Jain <kjain@linux.ibm.com>,
        K Prateek Nayak <kprateek.nayak@amd.com>,
        Sean Christopherson <seanjc@google.com>,
        Yanteng Si <siyanteng@loongson.cn>,
        Ravi Bangoria <ravi.bangoria@amd.com>,
        German Gomez <german.gomez@arm.com>,
        Changbin Du <changbin.du@huawei.com>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        liuwenyu <liuwenyu7@huawei.com>, linux-kernel@vger.kernel.org,
        linux-perf-users@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Wait until a lost sample occurs to allocate the lost samples buffer,
often the buffer isn't necessary. This saves a 64kb allocation and
5.3kb of peak memory consumption.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/builtin-record.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 9b4f3805ca92..b6c8c1371b39 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1924,21 +1924,13 @@ static void __record__save_lost_samples(struct record *rec, struct evsel *evsel,
 static void record__read_lost_samples(struct record *rec)
 {
 	struct perf_session *session = rec->session;
-	struct perf_record_lost_samples *lost;
+	struct perf_record_lost_samples *lost = NULL;
 	struct evsel *evsel;
 
 	/* there was an error during record__open */
 	if (session->evlist == NULL)
 		return;
 
-	lost = zalloc(PERF_SAMPLE_MAX_SIZE);
-	if (lost == NULL) {
-		pr_debug("Memory allocation failed\n");
-		return;
-	}
-
-	lost->header.type = PERF_RECORD_LOST_SAMPLES;
-
 	evlist__for_each_entry(session->evlist, evsel) {
 		struct xyarray *xy = evsel->core.sample_id;
 		u64 lost_count;
@@ -1961,6 +1953,14 @@ static void record__read_lost_samples(struct record *rec)
 				}
 
 				if (count.lost) {
+					if (!lost) {
+						lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+						if (!lost) {
+							pr_debug("Memory allocation failed\n");
+							return;
+						}
+						lost->header.type = PERF_RECORD_LOST_SAMPLES;
+					}
 					__record__save_lost_samples(rec, evsel, lost,
 								    x, y, count.lost, 0);
 				}
@@ -1968,9 +1968,18 @@ static void record__read_lost_samples(struct record *rec)
 		}
 
 		lost_count = perf_bpf_filter__lost_count(evsel);
-		if (lost_count)
+		if (lost_count) {
+			if (!lost) {
+				lost = zalloc(PERF_SAMPLE_MAX_SIZE);
+				if (!lost) {
+					pr_debug("Memory allocation failed\n");
+					return;
+				}
+				lost->header.type = PERF_RECORD_LOST_SAMPLES;
+			}
 			__record__save_lost_samples(rec, evsel, lost, 0, 0, lost_count,
 						    PERF_RECORD_MISC_LOST_SAMPLES_BPF);
+		}
 	}
 out:
 	free(lost);
-- 
2.42.0.758.gaed0368e0e-goog